‌ ‍ ‎ ‏ ‌ ‍ 's picture

‌ ‍ ‎ ‏ ‌ ‍

Maani

·

13xMaani

AI & ML interests

Novel Architectures | System Design

Recent Activity

new activity 3 days ago

allura-forge/Llama-3.3-8B-Instruct:This model is broken.

new activity 8 days ago

EssentialAI/rnj-1-instruct:gemma3 is absolutely trash.

liked a model 8 days ago

LiquidAI/LFM2-2.6B-Exp

View all activity

Organizations

None yet

upvoted a collection 19 days ago

Nemotron-Post-Training-v3

Collection of datasets used in the post-training phase of Nemotron Nano v3. • 7 items • Updated 11 days ago • 54

upvoted 2 collections 28 days ago

Olmo 3 Pre-training

All artifacts related to Olmo 3 pre-training • 10 items • Updated 11 days ago • 32

Olmo 3 Post-training

All artifacts for post-training Olmo 3. Datasets follow the model that resulted from training on them. • 32 items • Updated 11 days ago • 46

upvoted a changelog about 1 month ago

Changelog

Hugging Face Docs for Humans and AI Agents

Nov 6, 2025

• 86

upvoted a paper about 1 month ago

GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms

Paper • 2511.17592 • Published Nov 17, 2025 • 118

upvoted a changelog 3 months ago

Changelog

Repositories total file size is now displayed

Sep 18, 2025

• 175

upvoted an article 3 months ago

Article

Introducing Pivotal Token Search (PTS): Targeting Critical Decision Points in LLM Training

May 17, 2025

•

11

upvoted a paper 4 months ago

ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

Paper • 2508.18773 • Published Aug 26, 2025 • 16

upvoted a paper 6 months ago

Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models

Paper • 2506.19697 • Published Jun 24, 2025 • 44

upvoted an article 7 months ago

Article

Uncensor any LLM with abliteration

Jun 13, 2024

•

751

upvoted an article 8 months ago

Article

Tiny Agents: an MCP-powered agent in 50 lines of code

Apr 25, 2025

•

304

upvoted a paper 8 months ago

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float

Paper • 2504.11651 • Published Apr 15, 2025 • 31

upvoted an article 10 months ago

Article

DualPipe could be better without the Dual

Feb 28, 2025

•

17

upvoted a paper 11 months ago

o3-mini vs DeepSeek-R1: Which One is Safer?

Paper • 2501.18438 • Published Jan 30, 2025 • 23

upvoted an article 12 months ago

Article

So, what is general intelligence?

Jan 20, 2025

•

2

upvoted a collection 12 months ago

Tools 4 Agents

This is a collection of spaces on the hub that are useful for building agents. https://huggingface.co/docs/smolagents/en/tutorials/tools • 5 items • Updated Jun 26, 2025 • 7

upvoted a collection over 1 year ago

DataGemma Release

A series of pioneering open models that help ground LLMs in real-world data through Data Commons. • 2 items • Updated Jul 10, 2025 • 87

upvoted 2 papers about 2 years ago

Levels of AGI for Operationalizing Progress on the Path to AGI

Paper • 2311.02462 • Published Nov 4, 2023 • 37

Efficient LLM Inference on CPUs

Paper • 2311.00502 • Published Nov 1, 2023 • 7